MarginRankingLoss

class torch.nn.MarginRankingLoss(margin=0.0, size_average=None, reduce=None, reduction='mean') [source]

Creates a criterion that measures the loss given inputs x1x1 , x2x2 , two 1D mini-batch Tensors, and a label 1D mini-batch tensor yy (containing 1 or -1).

If y=1y = 1 then it assumed the first input should be ranked higher (have a larger value) than the second input, and vice-versa for y=1y = -1 .

The loss function for each pair of samples in the mini-batch is:

loss(x1,x2,y)=max(0,y(x1x2)+margin)\text{loss}(x1, x2, y) = \max(0, -y * (x1 - x2) + \text{margin})
Parameters
  • margin (float, optional) – Has a default value of 00 .
  • size_average (bool, optional) – Deprecated (see reduction). By default, the losses are averaged over each loss element in the batch. Note that for some losses, there are multiple elements per sample. If the field size_average is set to False, the losses are instead summed for each minibatch. Ignored when reduce is False. Default: True
  • reduce (bool, optional) – Deprecated (see reduction). By default, the losses are averaged or summed over observations for each minibatch depending on size_average. When reduce is False, returns a loss per batch element instead and ignores size_average. Default: True
  • reduction (string, optional) – Specifies the reduction to apply to the output: 'none' | 'mean' | 'sum'. 'none': no reduction will be applied, 'mean': the sum of the output will be divided by the number of elements in the output, 'sum': the output will be summed. Note: size_average and reduce are in the process of being deprecated, and in the meantime, specifying either of those two args will override reduction. Default: 'mean'
Shape:
  • Input1: (N)(N) where N is the batch size.
  • Input2: (N)(N) , same shape as the Input1.
  • Target: (N)(N) , same shape as the inputs.
  • Output: scalar. If reduction is 'none', then (N)(N) .

Examples:

>>> loss = nn.MarginRankingLoss()
>>> input1 = torch.randn(3, requires_grad=True)
>>> input2 = torch.randn(3, requires_grad=True)
>>> target = torch.randn(3).sign()
>>> output = loss(input1, input2, target)
>>> output.backward()

© 2019 Torch Contributors
Licensed under the 3-clause BSD License.
https://pytorch.org/docs/1.8.0/generated/torch.nn.MarginRankingLoss.html